AI agents invoke browser_press_key to trigger actions in Byob. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers browser actions by sending keyboard events to a real Chrome browser session. Keyboard events can trigger form submissions (Enter), navigation, UI interactions, and other operations whose effects depend on the current page state and key sent. This constitutes executing external operations in a live browser, warranting the Execute category.
From the tool's definition 'Send a single keyboard event to the page (e.g. Enter, Escape, Tab, F5, ArrowDown'
Attacks that exploit this kind of access
Send a single keyboard event to the page (e.g. Enter, Escape, Tab, F5, ArrowDown,. It is categorised as a Execute tool in the Byob MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Byob MCP server in PolicyLayer and add a rule for browser_press_key: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Byob. Nothing to install.
browser_press_key is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the browser_press_key rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for browser_press_key. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
browser_press_key is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.